Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 610 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6703. Min Range: -5.6703
Max Act: 5.6703. Min Act: -0.1700
Data Index: 7513714 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6703. Min Range: -5.6703
Max Act: 5.6391. Min Act: -0.1700
Data Index: 2609789 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6703. Min Range: -5.6703
Max Act: 5.5766. Min Act: -0.1700
Data Index: 5994766 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6703. Min Range: -5.6703
Max Act: 5.6391. Min Act: -0.1700
Data Index: 1602747 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6703. Min Range: -5.6703
Max Act: 5.5453. Min Act: -0.1700
Data Index: 1622528 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6703. Min Range: -5.6703
Max Act: 5.5453. Min Act: -0.1700
Data Index: 1680881 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6703. Min Range: -5.6703
Max Act: 5.5453. Min Act: -0.1700
Data Index: 3236998 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6703. Min Range: -5.6703
Max Act: 5.5453. Min Act: -0.1700
Data Index: 8688182 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6703. Min Range: -5.6703
Max Act: 5.5141. Min Act: -0.1700
Data Index: 7424763 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6703. Min Range: -5.6703
Max Act: 5.5141. Min Act: -0.1700
Data Index: 8172296 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6703. Min Range: -5.6703
Max Act: 5.4516. Min Act: -0.1700
Data Index: 6493040 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6703. Min Range: -5.6703
Max Act: 5.4828. Min Act: -0.1700
Data Index: 2445053 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6703. Min Range: -5.6703
Max Act: 5.4828. Min Act: -0.1700
Data Index: 4684301 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6703. Min Range: -5.6703
Max Act: 5.4516. Min Act: -0.1700
Data Index: 185661 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6703. Min Range: -5.6703
Max Act: 5.4516. Min Act: -0.1700
Data Index: 3166080 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6703. Min Range: -5.6703
Max Act: 5.5141. Min Act: -0.1700
Data Index: 2762661 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6703. Min Range: -5.6703
Max Act: 5.4516. Min Act: -0.1700
Data Index: 4328926 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6703. Min Range: -5.6703
Max Act: 5.4516. Min Act: -0.1700
Data Index: 4108036 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6703. Min Range: -5.6703
Max Act: 5.4516. Min Act: -0.1700
Data Index: 7937345 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6703. Min Range: -5.6703
Max Act: 5.4203. Min Act: -0.1700
Data Index: 8172815 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #19